© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 25-TRANSCODER-HP
    7. 108164
    Prev
    Next
    INDEX
    Explanations

    Dates and years

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tipping
    -0.29
    以èī²
    -0.27
     quantity
    -0.25
    CS
    -0.25
    Structure
    -0.25
     pro
    -0.24
     advocates
    -0.24
    å¯Ĩ度
    -0.24
    emp
    -0.24
    icky
    -0.24
    POSITIVE LOGITS
    Mos
    0.30
    æ¡£
    0.29
    -cycle
    0.26
    [ID
    0.25
    çī¹æ®ĬçļĦ
    0.25
    ä¹ı
    0.25
    _ZERO
    0.25
    ä¸įæİĴéĻ¤
    0.24
    lane
    0.24
    enez
    0.24
    Activations Density 2.086%

    No Known Activations